Text reuse is a common phenomenon in a variety of usergenerated content. Along with the quick expansion of social media, reuses of local text are occurring much more frequently than ever before. The task of detecting these local reuses serves as an essential step for many applications. It has attracted extensive attention in recent years. However, semantic level similarities have not received consideration in most previous works. In this paper, we introduce a novel method to efficiently detect local reuses at the semantic level for large scale problems. We propose to use continuous vector representations of words to capture the semantic level similarities between short text segments. In order to handle tens of billions of documents, methods based on information geometry and hashing methods are introduced to aggregate and map text segments presented by word embeddings to binary hash codes. Experimental results demonstrate that the proposed methods achieve significantly better performance than state-of-the-art approaches in all six document collections belonging to four different categories. At some recall levels, the precisions of the proposed method are even 10 times higher than previous methods. Moreover, the efficiency of the proposed method is comparable to or better than that of some other hashing methods.

No abstract